Soccer Analytics 2021 Review

Collection of the soccer analytics content that I liked the most in 2021!

The soccer analytics community is growing year after year. The potential of soccer data is not only catching the attention of researchers and amateur analysts but is also attracting more and more interest from soccer clubs. While the increased availability of freely available data and tools as well as the global pandemic led to an explosion of soccer analytics content in 2020, soccer clubs have arguably made a record-number of signings for data-related roles in 2021. Nevertheless, a significant number of high-quality blog posts and research papers has appeared in the past year. Like last year, this blog post provides an overview of the content that I liked the most!

As a result of the increased interest in soccer analytics, separating the wheat from the chaff has also become more challenging, especially for newcomers to the community. I keep track of the latest developments in the soccer analytics community primarily via Twitter, maintaining a list of soccer analytics people. This blog post lists my favorite soccer analytics content from the past year. If you believe your favorite research paper, blog post, webinar or podcast also deserves a spot in this review, then feel free to send me a direct message via Twitter or LinkedIn.

Research papers (50)

• Combining Machine Learning and Human Experts to Predict Match Outcomes in Football: A Baseline Model. Ryan Beal, Stuart Middleton, Timothy Norman, Sarvapali Ramchurn. Proceedings of the AAAI Conference on Artificial Intelligence. February 2021.
• A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer). Gabriel Anzer and Pascal Bauer. Frontiers in Sports and Active Living. March 2021.
• Enriching Event Data: A Semi-Supervised Augmentation Approach Using Location Information. Debangan Dey, Rahul Ghosal and Atanu Mitra. Stats Perform Pro Forum. March 2021.
• Identifying and Evaluating the Efficiency of Each Player During the Pressing Phase Against an Opponent’s Controlled Build-Up Play. Caterina De Bacco. Stats Perform Pro Forum. March 2021.
• A Physics Based Measurement of Defensive Contributions. Aditya Kothari. Stats Perform Pro Forum. March 2021.
• Volatility and Calculation of Risk-Adjusted Return in Football Scouting. Ola Lidmark Eriksson. Stats Perform Pro Forum. March 2021.
• Identifying and Evaluating Strategies for Successfully Penetrating a High Opposition Press from Short Goal Kicks, Played Inside the Box, to Move the Ball into the Opposition Half. Vignesh Jayanth. Stats Perform Pro Forum. March 2021.
• Routine Inspection: A Playbook for Corner Kicks. Laurie Shaw and Sudarshan Gopaladesikan. Proceedings of the 2021 MIT Sloan Sports Analytics Conference. April 2021.
• Leaving Goals on the Pitch: Evaluating Decision Making in Soccer. Maaike Van Roy, Pieter Robberechts, Wen-Chi Yang, Luc De Raedt and Jesse Davis. Proceedings of the 2021 MIT Sloan Sports Analytics Conference. April 2021.
• Making Offensive Play Predictable - Using a Graph Convolutional Network to Understand Defensive Performance in Soccer. Michael Stöckl, Thomas Seidl, Daniel Marley and Paul Power. Proceedings of the 2021 MIT Sloan Sports Analytics Conference. April 2021.
• A Poisson Betting Model with a Kelly Criterion Element for European Soccer. Kushal Shah, James Hyman and Dominic Samangy. Proceedings of the 2021 MIT Sloan Sports Analytics Conference. April 2021.
• How Soccer Scouts Identify Talented Players. Tom Bergkamp, Wouter Frencken, Susan Niessen, Rob Meijer and Ruud den Hartigh. European Journal of Sport Science. April 2021.
• Modelling Team Performance in Soccer Using Tactical Features Derived from Position Tracking Data. Floris Goes, Matthias Kempe, Jan van Norel and Koen Lemmink. IMA Journal of Management Mathematics. April 2021.
• From Motor Control to Team Play in Simulated Humanoid Football. Siqi Liu, Guy Lever, Zhe Wang, Josh Merel, Ali Eslami, Daniel Hennes, Wojciech Czarnecki, Yuval Tassa, Shayegan Omidshafiei, Abbas Abdolmaleki, Noah Siegel, Leonard Hasenclever, Luke Marris, Saran Tunyasuvunakool, Francis Song, Markus Wulfmeier, Paul Muller, Tuomas Haarnoja, Brendan Tracey, Karl Tuyls, Thore Graepel and Nicolas Heess. arXiv. May 2021.
• A Framework for the Fine-Grained Evaluation of the Instantaneous Expected Value of Soccer Possessions. Javier Fernández, Luke Bornn and Daniel Cervone. Machine Learning. May 2021.
• Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football. Ryan Beal, Georgios Chalkiadakis, Timothy Norman and Sarvapali Ramchurn. Proceedings of the International Conference on Autonomous Agents and Multiagent Systems. May 2021.
• SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos. Adrien Deliege, Anthony Cioppa, Silvio Giancola, Meisam Seikavandi, Jacob Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas Moeslund and Marc Van Droogenbroeck. CVPR 2021 International Workshop on Computer Vision in Sports (CVsports 2021). June 2021.
• Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts. Silvio Giancola and Bernard Ghanem. CVPR 2021 International Workshop on Computer Vision in Sports (CVsports 2021). June 2021.
• Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of Their Representations for Action Spotting. Anthony Cioppa, Adrien Deliege, Floriane Magera, Silvio Giancola, Olivier Barnich, Bernard Ghanem and Marc Van Droogenbroeck. CVPR 2021 International Workshop on Computer Vision in Sports (CVsports 2021). June 2021.
• A Risk-Reward Assessment of Passing Decisions: Comparison Between Positional Roles Using Tracking Data from Professional Men’s Soccer. Floris Goes, Edgar Schwarz, Marije Elferink-Gemser, Koen Lemmink and Michel Brink. Science and Medicine in Football. June 2021.
• Data-Driven Detection of Counterpressing in Professional Football. Pascal Bauer and Gabriel Anzer. Data Mining and Knowledge Discovery - Special Issue on Sports Analytics. July 2021.
• The Origins of Goals in the German Bundesliga. Pascal Bauer, Gabriel Anzer and Ulf Brefeld. Journal of Sports Sciences. July 2021.
• Towards Soccer Pass Feasibility Maps: The Role of Players’ Orientation. Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández, Gloria Haro and Coloma Ballester. Journal of Sports Sciences. August 2021.
• A Bayesian Approach to In-Game Win Probability in Soccer. Pieter Robberechts, Jan Van Haaren and Jesse Davis. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. August 2021.
• What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data. Charbel Merhej, Ryan Beal, Sarvapali Ramchurn and Tim Matthews. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. August 2021.
• Analyzing Learned Markov Decision Processes using Model Checking for Providing Tactical Advice in Professional Soccer. Maaike Van Roy, Wen-Chi Yang, Luc De Raedt and Jesse Davis. IJCAI 2021 Workshop on AI for Sports Analytics (AISA 2021). August 2021.
• Women’s Football Analyzed: Interpretable Expected Goals Models for Women. Lotte Bransen and Jesse Davis. IJCAI 2021 Workshop on AI for Sports Analytics (AISA 2021). August 2021.
• Why Would I Trust Your Numbers? On the Explainability of Expected Values in Soccer. Jan Van Haaren. IJCAI 2021 Workshop on AI for Sports Analytics (AISA 2021). August 2021.
• Evaluating Football Player: From Live Camera to Deep Reinforcement Learning. Théophane Gregoir and Paul Garnier. IJCAI 2021 Workshop on AI for Sports Analytics (AISA 2021). August 2021.
• Learning Football Body-Orientation as a Matter of Classification. Adrià Arbués-Sangüesa, Adrián Martín, Paulino Granero, Coloma Ballester and Gloria Haro. IJCAI 2021 Workshop on AI for Sports Analytics (AISA 2021). August 2021.
• Inferring the Strategy of Offensive and Defensive Play in Soccer with Inverse Reinforcement Learning. Pegah Rahimian and László Toka. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• Measuring the Effectiveness of Pressing in Soccer. Simon Merckx, Pieter Robberechts, Yannick Euvrard and Jesse Davis. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• The Interpretable Representation of Football Player Roles Based on Passing/Receiving Patterns. Arsalan Sattari, Ulf Johansson, Erik Wilderoth, Jasmin Jakupovic and Peter Larsson-Green. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• 6MapNet: Representing Soccer Players from Tracking Data by a Triplet Network. Hyunsung Kim, Jihun Kim, Dongwook Chung, Jonghyun Lee, Jinsung Yoon and Sang-Ki Ko. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• Similarity of Football Players Using Passing Sequences. Alberto Barbosa, Pedro Ribeiro and Inês Dutra. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• A Career in Football: What Is Behind an Outstanding Market Value?. Balázs Ács and László Toka. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• Predicting Player Transfers in the Small World of Football. Roland Kovács and László Toka. ECML/PKDD 2021 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA 2021). September 2021.
• Optimally Disrupting Opponent Build-Ups. Maaike Van Roy, Pieter Robberechts and Jesse Davis. StatsBomb Conference. October 2021.
• Potential Penetrative Pass (P3). Hadi Sotudeh. StatsBomb Conference. October 2021.
• Determining the Phases of Play Using Graph Neural Network Embeddings. Juan Camilo Campos. StatsBomb Conference. October 2021.
• The Quest for the Right Pass: Quantifying Players’ Decision Making. Borja Burriel and Javier Buldú. StatsBomb Conference. October 2021.
• Anatomy of Receiving and Turning with the Ball. Soumyajit Bose and Manas Saraswat. StatsBomb Conference. October 2021.
• Pace and Power: Removing Unconscious Bias from Soccer Broadcasts. Sam Gregory. New England Symposium on Statistics in Sports. October 2021.
• Player Masks: Encoding Soccer Decision-Making Tendencies. Devin Pleuler. New England Symposium on Statistics in Sports. October 2021.
• Predictive Value of Off-Target Shots in Soccer. Ethan Baron. New England Symposium on Statistics in Sports. October 2021.
• Estimating the Change in Soccer… Home Advantage During the COVID-19 Pandemic. Luke Benz and Mike Lopez. New England Symposium on Statistics in Sports. October 2021.
• Extended Model for Expected Threat in Soccer. Jirka Poropudas. New England Symposium on Statistics in Sports. October 2021.
• A Copula-Based Hidden Markov Model for Classification of Tactics in Football. Marius Oetting. New England Symposium on Statistics in Sports. October 2021.
• Quantifying League-Independent Scoring Ability in Soccer. Daniel Daly-Grafstein. New England Symposium on Statistics in Sports. October 2021.
• The Statistics of Spin in Soccer. Jackson Weaver. New England Symposium on Statistics in Sports. October 2021.

Blog posts (40)

• Valuing Actions: Knowing When Your Model Doesn’t Have a Clue. Charles William. openGoal. February 2021.
• The Seven Styles of Soccer. John Muller. Space Space Space. February 2021.
• Shape Analysis: Automatically Detecting Formations. Jonny Whitmore and Thomas Seidl. Stats Perform. February 2021.
• Quantifying Player Contribution to Counter Attacks. Laurynas Raudonius. Stats Perform Pro Forum. March 2021.
• The State of MLS Analytics Ahead of the 2021 Season. Eliot McKinley. American Soccer Analysis. March 2021.
• Paper Implementation: Interpretable Prediction of Goals in Soccer. Abhishek Sharma. Abhishek Sharma. April 2021.
• Towards Crowdsourced Tracking Data?. Lars Maurath. The Significant Game. April 2021.
• Soccer at Sloan 2021: A Summary. Mark Thompson. Get Goalside!. May 2021.
• Barnsley is Doing Moneyball Right and It’s Ruining Soccer. John Muller. Space Space Space. May 2021.
• Tools for Tiny Teams. Ben Torvaney. Stats and Snakeoil. May 2021.
• Analytics Is Older Than You Think: (Re)Introducing Charles Reep. Mark Thompson. Get Goalside!. May 2021.
• Everything You Need to Know About ‘Pitch Control’. Mark Thompson. Get Goalside!. May 2021.
• Intent Vs. Outcome: Adding Another Layer to Expected Possession Value. Aditya Kothari. The Come On Man. June 2021.
• What Can Time-Discount Rates Tell Us about xG and Goals?. Ben Torvaney. Stats and Snakeoil. June 2021.
• Predicting the Success of a Transfer. Aditya Kothari. The Come On Man. June 2021.
• The Value of Disruptive Runs. Or, Why Firmino Is Such a Valuable Player for Liverpool. David Sumpter. David Sumpter. June 2021.
• How to Estimate Team Strength from xG Totals. Ben Torvaney. Stats and Snakeoil. June 2021.
• Sports Analytics Reading List. Brendan Kent. Tech & Data & Sports. June 2021.
• On Tracking Data, the Nature of Soccer, and Allocation. Tiotal Football. Absolute Unit. July 2021.
• Versatile Verification of Soccer Analytics Models. Laurens Devos, Wannes Meert, Pieter Robberechts and Jesse Davis. DTAI Sports Analytics Lab. July 2021.
• Space Recruits, Part 1: The State of Analytics. John Muller. Space Space Space. July 2021.
• Space Recruits, Part 2: Data Scouting on a Budget. John Muller. Space Space Space. July 2021.
• We Have a New Win Probability Model. Tyler Richardett. American Soccer Analysis. July 2021.
• Where Goals Come From: Using Past Goals to Create Future Goals. Jamon Moore and Carl Carpenter. American Soccer Analysis. August 2021.
• Not All Duels Are Created Equal, Nor Are They Easy to Adjust. Mark Thompson. Get Goalside!. August 2021.
• A Bayesian Approach to In-Game Win Probability. Pieter Robberechts, Jan Van Haaren and Jesse Davis. DTAI Sports Analytics Lab. August 2021.
• Theory of Transfer Fees. Tiotal Football. Absolute Unit. September 2021.
• The Who, the What, and the Why of Bringing Advanced Stats to the Public. Mark Thompson. Get Goalside!. September 2021.
• Brexitball: The Effects of GBE Restrictions on the English Football Market. Andy Watson. Analytics FC. October 2021.
• Measuring Transfer Success Through Minutes Played. Josh Hobbs. Analytics FC. October 2021.
• Conference Season, Autumn 2021 - the What & the How. Mark Thompson. Get Goalside!. October 2021.
• Where to Spend Your Analytics Money?. Mark Thompson. Get Goalside!. October 2021.
• Measuring Transfer Success Through Goal Difference Added. Josh Hobbs. Analytics FC. November 2021.
• Should We Stop Using Moving Averages?. Ben Torvaney. Stats and Snakeoil. November 2021.
• How to Hire Your First Data Scientist. Mikhail Zhilkin. Training Ground Guru. November 2021.
• Do Some Leagues Overpay for Talent?. Josh Hobbs. Analytics FC. December 2021.
• Jérémy Doku and Using AI to Predict the Success of Transfers. Jens Melvang, Joe Gallagher and Daniel Dinsdale. Training Ground Guru. November 2021.
• Release Time, and Expected Expected Goals. Mark Thompson. Get Goalside!. November 2021.
• Theory of Soccer Pt. 1: The Prevailing Orthodox Theories of Soccer. Tiotal Football. Absolute Unit. December 2021.
• Theory of Soccer Pt 2: The Abstract. Tiotal Football. Absolute Unit. December 2021.

News articles (11)

• Possession: The Most Dangerous Statistic in Football. Mark Carey and Tom Worville. The Athletic. January 2021.
• Data Experts Are Becoming Football’s Best Signings. Justin Harper. BBC. March 2021.
• Soccer Is Learning To See The Whole Game. John Muller. FiveThirtyEight. March 2021.
• Is Soccer Wrong About Long Shots?. John Muller. FiveThirtyEight. April 2021.
• Introducing ‘Expected Threat’ (or xT), the New Metric on the Block. Tom Worville. The Athletic. August 2021.
• Possession Is The Puzzle Of Soccer Analytics: These Models Are Trying To Solve It. John Muller. FiveThirtyEight. September 2021.
• How Football’s Finest Are Using Analytics to Find an Edge. Tom Worville. The Athletic. October 2021.
• Soccer Looks Different When You Can’t See Who’s Playing. John Muller. FiveThirtyEight. November 2021.
• To Duel or Not to Duel: Does Winning Your Battles Win You More Games?. Tom Worville. The Athletic. November 2021.
• What’s so Special about the Half-Spaces? (With Help from René Marić). John Muller. The Athletic. November 2021.
• Introducing the No-Touch All-Stars. John Muller. The Athletic. December 2021.

Webinars (9)

• A Keeper: The Evolution of Soccer Analytics with Heather O’Reilly, Ted Knutson, Ravi Ramineni and Gregg Berhalter. MIT Sloan Sports Analytics Conference. April 2021.
• Data Visualisation Is about Words with John Burn-Murdoch. Friends of Tracking. April 2021.
• Neural Networks for Understanding Defending with Paul Power. Friends of Tracking. April 2021.
• What Do Data Analysts and Data Scientists Do at a Football Club? with Hannah Roberts, Ashwin Raman, Sam Gregory and Rob Suddaby. Friends of Tracking. May 2021.
• The Future of Possession Value Models with Matthias Kullowatz and Jernej Flisar. Friends of Tracking. May 2021.
• How Data Is Reshaping Football Journalism with Tom Worville. Friends of Tracking. June 2021.
• Visualising and Clustering Passes with Maram AlBaharna. Friends of Tracking. July 2021.
• Football’s New Stat - What is Expected Threat? with Tifo Football. Tifo Football. September 2021.
• How Brentford’s Moneyball Approach Works with Tifo Football. Tifo Football. October 2021.

Podcasts (3)

• Expected Goals in Football Manager: How They Work with Jan Van Haaren. Zealand. February 2021.
• Sounders Head of Analytics Provides a Peek Behind Curtain with Ravi Ramineni. Sounder at Heart Podcast Network. June 2021.
• The Future of Data Science in Football with Luke Bornn. Training Ground Guru Podcast. September 2021.

Events (8)

• Stats Perform Pro Forum. 25 March 2021.
• MIT Sloan Sports Analytics Conference. 8-9 April 2021.
• Workshop on Computer Vision in Sports. 25 June 2021.
• Workshop on AI for Sports Analytics. 17 August 2021.
• Workshop on Machine Learning and Data Mining for Sports Analytics. 13 September 2021.
• New England Symposium on Statistics in Sports. October 2021.
• StatsBomb Conference. 8 October 2021.
• Analytics in Sports Tomorrow. 11 November 2021.